Malware Makeover: Breaking ML-based Static Analysis by Modifying Executable Bytes

1 code implementation • 19 Dec 2019 • Keane Lucas, Mahmood Sharif, Lujo Bauer, Michael K. Reiter, Saurabh Shintre

Moreover, we found that our attack can fool some commercial anti-viruses, in certain cases with a success rate of 85%.

Feature Engineering Malware Detection +1

Deep Detector Health Management under Adversarial Campaigns

no code implementations • 19 Nov 2019 • Javier Echauz, Keith Kenemer, Sarfaraz Hussein, Jay Dhaliwal, Saurabh Shintre, Slawomir Grzonkowski, Andrew Gardner

Machine learning models are vulnerable to adversarial inputs that induce seemingly unjustifiable errors.

Domain Adaptation Management

Gradient Similarity: An Explainable Approach to Detect Adversarial Attacks against Deep Learning

no code implementations • 27 Jun 2018 • Jasjeet Dhaliwal, Saurabh Shintre

Deep neural networks are susceptible to small-but-specific adversarial perturbations capable of deceiving the network.

Detecting Adversarial Samples from Artifacts

3 code implementations • 1 Mar 2017 • Reuben Feinman, Ryan R. Curtin, Saurabh Shintre, Andrew B. Gardner

Deep neural networks (DNNs) are powerful nonlinear architectures that are known to be robust to random perturbations of the input.

Density Estimation